Back to skill
v1.0.0

UnSearch

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:36 AM.

Analysis

UnSearch is a coherent instruction-only web search skill with expected API-key and external-provider data flows, but users should protect the key and treat retrieved web content as untrusted.

GuidanceThis skill appears safe to install if you want UnSearch web search and research capabilities. Before using it, protect the UNSEARCH_API_KEY, avoid sending sensitive searches or private URLs unless you trust the provider, and make sure the agent treats scraped web pages as information sources rather than instructions.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Agent Goal Hijack
SeverityLowConfidenceHighStatusNote
SKILL.md
"scrape_content": true ... "scraped_content": { "text": "Full page content..." }

The skill retrieves full web page content for agent use; that content may contain untrusted instructions or misleading text.

User impactA web page returned by the API could include text that tries to influence the agent if the agent treats retrieved content as instructions.
RecommendationTreat search results and scraped content as data, not as agent instructions; verify important claims with multiple sources.
Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse
SeverityLowConfidenceHighStatusNote
SKILL.md
All requests require header: `X-API-Key: $UNSEARCH_API_KEY`

The skill requires an UnSearch API key to authenticate requests; this is expected for the service but is still a credential.

User impactAnyone who obtains the API key may be able to use the user's UnSearch quota or account access.
RecommendationStore the API key securely, avoid sharing it in prompts or logs, and rotate it if it may have been exposed.
Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication
SeverityLowConfidenceHighStatusNote
SKILL.md
**Base URL:** `https://api.unsearch.dev/api/v1` ... `query`: "your search query" ... `urls`: ["https://example.com/article"]

Queries and URLs are sent to an external UnSearch API provider, which is central to the skill's purpose.

User impactSearch terms, URLs, and research topics may be visible to the external API provider.
RecommendationAvoid sending confidential queries or private URLs unless the provider's privacy and retention practices are acceptable.